© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-RES-MATRYOSHKA-DC
    7. 582
    Prev
    Next
    INDEX
    Explanations

    words related to information about a collection of patients or experiment participants

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynchronously
    -0.66
    WebServlet
    -0.63
    Bảo
    -0.63
    Sucesor
    -0.60
    Revenir
    -0.58
     Ballo
    -0.57
    setToken
    -0.57
    rrggbb
    -0.56
    databind
    -0.56
     Fällen
    -0.56
    POSITIVE LOGITS
     characteristics
    1.20
     attributes
    1.06
     Characteristics
    1.03
     properties
    0.98
    characteristics
    0.98
    Characteristics
    0.93
     Attributes
    0.91
     particulars
    0.91
     traits
    0.90
     details
    0.88
    Activations Density 1.418%

    No Known Activations